A Comprehensive Survey of Deep Learning in Remote Sensing: Theories, Tools and Challenges for the Community

Abstract

In recent years, deep learning (DL), a re-branding of neural networks (NNs), has risen to the top in numerous areas, namely computer vision (CV), speech recognition, natural language processing, etc. Whereas remote sensing (RS) possesses a number of unique challenges, primarily related to sensors and applications, inevitably RS draws from many of the same theories as CV; e.g., statistics, fusion, and machine learning, to name a few. This means that the RS community should be aware of, if not at the leading edge of, of advancements like DL. Herein, we provide the most comprehensive survey of state-of-the-art RS DL research. We also review recent new developments in the DL field that can be used in DL for RS. Namely, we focus on theories, tools and challenges for the RS community. Specifically, we focus on unsolved challenges and opportunities as it relates to (i) inadequate data sets, (ii) human-understandable solutions for modelling physical phenomena, (iii) Big Data, (iv) non-traditional heterogeneous data sources, (v) DL architectures and learning algorithms for spectral, spatial and temporal data, (vi) transfer learning, (vii) an improved theoretical understanding of DL systems, (viii) high barriers to entry, and (ix) training and optimizing the DL.

arXiv comment64 pages, 411 references. To appear in Journal of Applied Remote Sensing

References in corpus (11)

• Deep Learning in Neural Networks: An Overview
• Remote Sensing Image Scene Classification: Benchmark and State of the Art
• A Survey on Object Detection in Optical Remote Sensing Images
• PCANet: A Simple Deep Learning Baseline for Image Classification?
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• Towards Better Exploiting Convolutional Neural Networks for Remote Sensing Scene Classification
• Advances in Hyperspectral Image Classification: Earth monitoring with statistical learning methods
• Unsupervised Deep Feature Extraction for Remote Sensing Image Classification
• Recent Advances in Domain Adaptation for the Classification of Remote Sensing Data
• Deep convolutional neural networks for pedestrian detection
• Spectral-Spatial Classification of Hyperspectral Image Using Autoencoders

Cited by in corpus (23)

• A Review on Deep Learning in UAV Remote Sensing
• Medical Deep Learning -- A systematic Meta-Review
• An Attention-Fused Network for Semantic Segmentation of Very-High-Resolution Remote Sensing Imagery
• Spatially Continuous and High-resolution Land Surface Temperature: A Review of Reconstruction and Spatiotemporal Fusion Techniques
• A CNN Approach to Simultaneously Count Plants and Detect Plantation-Rows from UAV Imagery
• Convolutional Neural Networks for Global Human Settlements Mapping from Sentinel-2 Satellite Imagery
• Current Trends in Deep Learning for Earth Observation: An Open-source Benchmark Arena for Image Classification
• CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding
• Self-Supervised Multisensor Change Detection
• RSAM-Seg: A SAM-based Approach with Prior Knowledge Integration for Remote Sensing Image Semantic Segmentation
• Automatic extraction of road intersection points from USGS historical map series using deep convolutional neural networks
• High-resolution canopy height map in the Landes forest (France) based on GEDI, Sentinel-1, and Sentinel-2 data with a deep learning approach
• A Multiple Classifier Approach for Concatenate-Designed Neural Networks
• A Comparison and Strategy of Semantic Segmentation on Remote Sensing Images
• A benchmark dataset for deep learning-based airplane detection: HRPlanes
• Complex data labeling with deep learning methods: Lessons from fisheries acoustics
• A generic self-supervised learning (SSL) framework for representation learning from spectra-spatial feature of unlabeled remote sensing imagery
• A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery
• SatImNet: Structured and Harmonised Training Data for Enhanced Satellite Imagery Classification
• Spatially explicit accuracy assessment of deep learning-based, fine-resolution built-up land data in the United States
• Deep learning for cosmological parameter inference from a dark matter halo density field
• On the Importance of 3D Surface Information for Remote Sensing Classification Tasks
• Deep Learning -- A first Meta-Survey of selected Reviews across Scientific Disciplines, their Commonalities, Challenges and Research Impact